{"id":"W3164449140","doi":"10.18280/ria.350206","title":"AksharaNet: A GPU Accelerated Modified Depth-Wise Separable Convolution for Kannada Text Classification","year":2021,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Artificial intelligence; Convolutional neural network; Grayscale; Convolution (computer science); Character (mathematics); Pattern recognition (psychology); Kannada; Search engine indexing; Deep learning; Scale (ratio); Key (lock); Artificial neural network; Image (mathematics); Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002551733,0.0008888087,0.0005294573,0.0006965044,0.0003358957,0.0007460525,0.001611429,0.0005806396,0.004482244],"category_scores_gemma":[0.0007293914,0.0002348311,0.0005613955,0.0007391192,0.0002112552,0.001185155,0.0007622747,0.0008636745,0.002088652],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005314281,"about_ca_system_score_gemma":0.0009268033,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007628661,"about_ca_topic_score_gemma":0.01167922,"domain_scores_codex":[0.9998311,0.00001851093,0.00001021886,0.00004959969,0.00005873836,0.00003174098],"domain_scores_gemma":[0.9998456,0.0000298457,0.00001264882,0.00003723341,0.00005291853,0.00002167299],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007366642,0.0003561442,0.002892324,0.0003374915,0.0002359571,0.0003607783,0.0001312503,0.06729782,0.05310677,0.003059664,0.03734974,0.8341354],"study_design_scores_gemma":[0.00004447782,0.0002545741,0.001295455,0.00001809191,0.00003765303,0.000261233,0.00005096932,0.960602,0.02421451,0.001420156,0.01177705,0.000023829],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2875108,0.003546154,0.6372344,0.0006638595,0.0009380159,0.0005045231,0.003817309,0.04690873,0.01887627],"genre_scores_gemma":[0.4961983,0.0009523622,0.4619364,0.0004291967,0.0001018166,0.0003243158,0.01197228,0.0009134123,0.02717194],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007628661,"threshold_uncertainty_score":0.01516849,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1011066947702319,"score_gpt":0.3153051932894518,"score_spread":0.2141984985192198,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}